Improving Risk Stratification in Hypertrophic Cardiomyopathy: A Novel Score Combining Echocardiography, Clinical, and Medication Data

2026-03-27

AI Summary

Current risk stratification tools for hypertrophic cardiomyopathy (HCM), such as the ESC score, exhibit limited discriminative capacity, hindering precise guidance for implantable cardioverter-defibrillator (ICD) placement and longitudinal follow-up. This study addresses this gap by developing the first interpretable machine learning–based risk scoring model that leverages echocardiographic, clinical, and medication data from electronic health records to predict 5-year composite cardiovascular event risk in HCM patients and support ongoing monitoring. Using a random forest ensemble approach, the model achieved an internal AUC of 0.85 ± 0.02, significantly outperforming the ESC score (0.56 ± 0.03). External validation confirmed robust risk stratification performance (Log-rank p = 8.62 × 10⁻⁴), with stable calibration in event-free populations, offering a superior tool for clinical decision-making.

Abstract

Hypertrophic cardiomyopathy (HCM) requires accurate risk stratification to inform decisions regarding ICD therapy and follow-up management. Current established models, such as the European Society of Cardiology (ESC) score, exhibit moderate discriminative performance. This study develops a robust, explainable machine learning (ML) risk score leveraging routinely collected echocardiographic, clinical, and medication data, typically contained within Electronic Health Records (EHRs), to predict a 5-year composite cardiovascular outcome in HCM patients. The model was trained and internally validated using a large cohort (N=1,201) from the SHARE registry (Florence Hospital) and externally validated on an independent cohort (N=382) from Rennes Hospital. The final Random Forest ensemble model achieved a high internal Area Under the Curve (AUC) of 0.85 +- 0.02, significantly outperforming the ESC score (0.56 +- 0.03). Critically, survival curve analysis on the external validation set showed superior risk separation for the ML score (Log-rank p = 8.62 x 10^(-4) compared to the ESC score (p = 0.0559). Furthermore, longitudinal analyses demonstrate that the proposed risk score remains stable over time in event-free patients. The model high interpretability and its capacity for longitudinal risk monitoring represent promising tools for the personalized clinical management of HCM.

Problem

• Hypertrophic Cardiomyopathy
• Risk Stratification
• Cardiovascular Outcome Prediction
• ICD Therapy
• ESC Score

Innovation

• machine learning
• risk stratification
• hypertrophic cardiomyopathy
• explainable AI
• electronic health records